© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 755
    Prev
    Next
    INDEX
    Explanations

    concepts related to considerations and factors taken into account in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "[Something] should be considered when..."

    np_acts-logits-general · gemini-2.0-flash

    when considering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.71
    
    -0.67
     intptr
    -0.60
     jScrollPane
    -0.58
    extAlignment
    -0.56
    AddHtmlAttribute
    -0.55
    GraphicsUnit
    -0.54
    ThroughAttribute
    -0.51
    scalatest
    -0.50
    /*
    -0.49
    POSITIVE LOGITS
     when
    1.83
     lors
    1.77
     during
    1.66
    during
    1.49
    when
    1.44
     هنگام
    1.43
     beim
    1.39
     podczas
    1.38
     DURING
    1.35
     أثناء
    1.33
    Activations Density 0.967%

    No Known Activations